Multimodal Machine Learning-Based Clinical and Genomic Prognostic Factors for Progression-Free Survival in Metastatic Breast Cancer Using Phase III MONALEESA Trials
- 1Novartis Pharmaceuticals Corporation
Abstract
PurposeCyclin-dependent kinase 4/6 inhibitors in combination with endocrine therapy have become widely adopted as a first-line treatment approach for hormone receptor-positive (HR+)/human epidermal growth factor receptor 2-negative (HER2-) advanced breast cancer (ABC). Through a collaboration between Novartis and the US Food and Drug Administration, we integrated multimodal data from phase III MONALEESA trials to identify novel prognostic factors for HR+/HER2-ABC.
Experimental DesignBaseline clinical and genomics data were collected from patients in the MONALEESA-2, -3, and -7 trials. Circulating tumor DNA (ctDNA) from plasma samples and gene expression in archival tumor biopsies were analyzed. Machine learning models were trained (n = 1,355) on progression-free survival (PFS) using multimodal features via fusion models. In a test set (n = 382), prognostic performances were evaluated using the Kaplan-Meier, Cox, and Weibull models.
ResultsThe late fusion model achieved a prognostic performance (C-index: 0.727, 95% CI: 0.641-0.799) slightly outperforming early fusion (C-index: 0.718, 95% CI: 0.631-0.791) and single-modality models. Model-based risk stratification identified distinct low- and high-risk groups (PFS HR, 0.28; 95% CI: 0.20-0.38). Among the top 40 features for progression risk (18 clinical, 20 gene expression, and 2 ctDNA), these were associated with higher risk: liver involvement, higher histological grades, early relapse; lower STC2 and RBBP8 expressions and higher FBX05 expression; and higher tumor mutational burden and ctDNA purity.
ConclusionsIntegrating clinical and genomic modalities improved progression risk prediction compared with single-modality models, while highlighting salient features that inform the underlying biology and support hypothesis generation.
Related
- Baseline 25-hydroxyvitamin D and progression-free survival in de novo metastatic hormone-sensitive prostate cancer: prognostic model development and external validation.
- Peripheral blood mRNA-based prognostic model for progression to metastatic castration-resistant prostate cancer and identification of SLC6A8 as a glycolysis-promoting biomarker
- Systematic Modality Ablation of Multimodal Machine Learning for Predicting 24-Month Progression from Mild Cognitive Impairment to Alzheimer's Disease
- Prognostic significance and clinicopathologic prediction of tumor deposits in non-metastatic colon mucinous adenocarcinoma
- Prognostic Significance of CD47 and DHX9 in Metastatic Rectal Cancer
BibTeX
@misc{wang2026multimodal,
title = {{Multimodal Machine Learning-Based Clinical and Genomic Prognostic Factors for Progression-Free Survival in Metastatic Breast Cancer Using Phase III MONALEESA Trials}},
author = {C. Wang and R. Paul and Y. Li and S. Smith and Q. Cao and S. H. Chang and R. Charlab and T. Coroller and R. Huang and L. Amiri-Kordestani and Z. Li and Q. Liu and C. Osgood and S. Peyrard and B. Sahiner and L. Santana-Quintero and F. Su and J. P. Zarate and H. Zhu and D. Ohlssen and N. Petrick and A. Amatya and N. Solovieff},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.09.26364892},
url = {https://www.medrxiv.org/content/10.64898/2026.10.09.26364892v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Multimodal Machine Learning-Based Clinical and Genomic Prognostic Factors for Progression-Free Survival in Metastatic Breast Cancer Using Phase III MONALEESA Trials
AU - C. Wang
AU - R. Paul
AU - Y. Li
AU - S. Smith
AU - Q. Cao
AU - S. H. Chang
AU - R. Charlab
AU - T. Coroller
AU - R. Huang
AU - L. Amiri-Kordestani
AU - Z. Li
AU - Q. Liu
AU - C. Osgood
AU - S. Peyrard
AU - B. Sahiner
AU - L. Santana-Quintero
AU - F. Su
AU - J. P. Zarate
AU - H. Zhu
AU - D. Ohlssen
AU - N. Petrick
AU - A. Amatya
AU - N. Solovieff
PY - 2026
DA - 2026/10/09
PB - medRxiv
DO - 10.64898/2026.10.09.26364892
UR - https://www.medrxiv.org/content/10.64898/2026.10.09.26364892v1
AB - PurposeCyclin-dependent kinase 4/6 inhibitors in combination with endocrine therapy have become widely adopted as a first-line treatment approach for hormone receptor-positive (HR+)/human epidermal growth factor receptor 2-negative (HER2-) advanced breast cancer (ABC). Through a collaboration between Novartis and the US Food and Drug Administration, we integrated multimodal data from phase III MONALEESA trials to identify novel prognostic factors for HR+/HER2-ABC. Experimental DesignBaseline clinical and genomics data were collected from patients in the MONALEESA-2, -3, and -7 trials. Circulating tumor DNA (ctDNA) from plasma samples and gene expression in archival tumor biopsies were analyzed. Machine learning models were trained (n = 1,355) on progression-free survival (PFS) using multimodal features via fusion models. In a test set (n = 382), prognostic performances were evaluated using the Kaplan-Meier, Cox, and Weibull models. ResultsThe late fusion model achieved a prognostic performance (C-index: 0.727, 95% CI: 0.641-0.799) slightly outperforming early fusion (C-index: 0.718, 95% CI: 0.631-0.791) and single-modality models. Model-based risk stratification identified distinct low- and high-risk groups (PFS HR, 0.28; 95% CI: 0.20-0.38). Among the top 40 features for progression risk (18 clinical, 20 gene expression, and 2 ctDNA), these were associated with higher risk: liver involvement, higher histological grades, early relapse; lower STC2 and RBBP8 expressions and higher FBX05 expression; and higher tumor mutational burden and ctDNA purity. ConclusionsIntegrating clinical and genomic modalities improved progression risk prediction compared with single-modality models, while highlighting salient features that inform the underlying biology and support hypothesis generation.
ER -